Judicial nested named entity recognition method with MRC framework

•Introduce the machine reading comprehension framework into the named entity recognition in the judicial field, and propose a method based on the machine reading comprehension, which effectively solves the problem of nested entities in legal texts.•Explore different question construction templates for each entity type and construct a legal named entity recognition dataset based on machine reading comprehension format.•The experimental results on the CAIL-IE dataset show that the proposed method achieves significant improvements than other state-of-the-art baselines.